Natural Hazards

, Volume 88, Issue 3, pp 1591–1607 | Cite as

A data-driven approach to assess large fire size generation in Greece

  • Ioannis Mitsopoulos
  • Giorgos Mallinis
Original Paper


Identifying factors and drivers which control large fire size generation is critical for planning fire management activities. This study attempts to determine the role of fire suppression tactics and behavior, weather, topography and landscape features on two different datasets of large fire size (500–1000 ha) and very large fire size (>1000 ha) compared to two datasets of small fire size (<50 ha) which occurred in Greece, during the period 1984–2009. In this context, we used a logistic regression (LR) analysis and two machine learning algorithms: random forest (RF) and boosting classification trees (BCT). The models comparison was based on the area under the receiver operating characteristic curve and the observed overall accuracy. The comparison indicated that RF had greater ability than LR and BCT to predict large fire generation. Results from the RF classifier algorithm showed that large fire generation mainly depended on fire suppression tactics and the prevailing weather conditions. This improved understanding of the factors which drive fire ignitions to turn into large fire sizes will provide the opportunity for land and forest managers to increase fire awareness and the development of concrete initiatives for successful fire management.


Large fires Fire management Machine learning Greece 



We would like to thank the two anonymous reviewers whose insightful comments helped to substantially improve this manuscript.


  1. Aguado I, Chuvieco E, Boren R, Nieto H (2007) Estimation of dead fuel moisture content from meteorological data in Mediterranean areas. Applications in fire danger assessment. Int J Wildland Fire 16:390–397CrossRefGoogle Scholar
  2. Barbero R, Abatzoglou J, Steel E (2014a) Modeling very large-fire occurrences over the continental United States from weather and climate forcing. Environ Res Lett 9:124009CrossRefGoogle Scholar
  3. Barbero R, Abatzoglou J, Kolden C, Hegewisch K, Larkin N, Podschwit H (2014b) Multi-scalar influence of weather and climate on very large-fires in the eastern United States. Int J Climatol 35:2180–2186CrossRefGoogle Scholar
  4. Barros A, Pereira J, Lund U (2012) Identifying geographical patterns of wildfire orientation: a watershed-based analysis. For Ecol Manag 264:98–107CrossRefGoogle Scholar
  5. Bermudez Z, Mendes J, Pereira J, Turkman K, Vasconcelos M (2009) Spatial and temporal extremes of wildfire sizes in Portugal. Int J Wildland Fire 18:983–991CrossRefGoogle Scholar
  6. Bessie W, Johnson E (1995) The relative importance of fuels and weather on fire behavior in subalpine forests. Ecology 76:747–762CrossRefGoogle Scholar
  7. Bradstock R, Cohn J, Gill A, Bedward M, Lucas C (2009) Prediction of the probability of large fires in the Sydney region of south-eastern Australia using fire weather. Int J Wildland Fire 18:932–943CrossRefGoogle Scholar
  8. Breiman L (2001) Random forests. Mach Learn 45:5–32CrossRefGoogle Scholar
  9. Cardille J, Ventura S, Turner M (2001) Environmental and social factors influencing wildfires in the upper Midwest, United States. Ecol Appl 11:111–127CrossRefGoogle Scholar
  10. Catry F, Rego F, Bação F, Moreira F (2009) Modelling and mapping wildfire ignition risk in Portugal. Int J Wildland Fire 18:921–931CrossRefGoogle Scholar
  11. Costafreda-Aumedes S, Cardil A, Molina D, Daniel S, Mavsar R, Vega-Garcia C (2015) Analysis of factors influencing deployment of fire suppression resources in Spain using artificial neural networks. iForest 9:138–145CrossRefGoogle Scholar
  12. Curt T, Borgniet L, Bouillon C (2013) Wildfire frequency varies with the size and shape of fuel types in southeastern France: implications for environmental management. J Environ Manag 117:150–161CrossRefGoogle Scholar
  13. Deeming J, Burgan R, Cohen J (1977) The national fire-danger rating system: 1978. In: General techical report INT-39. USDA Forest Service, Intermountain Forest and Range Experiment Station, OgdenGoogle Scholar
  14. Díaz-Delgado R, Lloret F, Pons X (2004) Spatial patterns of fire occurrence in Catalonia, NE, Spain. Landsc Ecol 19:731–745CrossRefGoogle Scholar
  15. Dickson B, Prather J, Xu Y, Hampton H, Aumack E (2006) Large fire occurrence in Northern Arizona, USA. Landsc Ecol 21:747–761CrossRefGoogle Scholar
  16. Dilts T (2015) Topography tools for ArcGIS 10.1. University of Nevada Reno. Assessed 10 Oct 2016
  17. Dimitrakopoulos A (2001) PYROSTAT—a computer program for forest fire data inventory and analysis in Mediterranean countries. Environ Model Softw 16:351–359CrossRefGoogle Scholar
  18. Dimitrakopoulos A, Gogi C, Stamatelos G, Mitsopoulos I (2011) Statistical analysis of the fire environment of large forest fires (>1000 ha) in Greece. Pol J Environ Stud 20:327–332Google Scholar
  19. Duane A, Piqué M, Castellnou M, Brotons L (2015) Predictive modelling of fire occurrences from different fire spread patterns in Mediterranean landscapes. Int J Wildland Fire 24:407–418CrossRefGoogle Scholar
  20. Duro D, Franklin S, Dube M (2012) Multi-scale object-based image analysis and feature selection of multi-sensor earth observation imagery using random forests. Int J Remote Sens 33:4502–4526CrossRefGoogle Scholar
  21. Dyer J (2009) Assessing topographic patterns in moisture use and stress using a water balance approach. Landsc Ecol 24:391–403CrossRefGoogle Scholar
  22. Fawcett T (2006) An introduction to ROC analysis. Pattern Recognit Lett 27:861–874CrossRefGoogle Scholar
  23. Feng L, Yang J, Zu J, Zhang J (2015) Quantifying influences and relative importance of fire weather, topography, and vegetation on fire size and fire severity in a Chinese boreal forest landscape. For Ecol Manag 356:2–12CrossRefGoogle Scholar
  24. Fernandes P, Luz A, Loureiro C (2010) Changes in wildfire severity from maritime pine woodland to contiguous forest types in the mountains of northwestern Portugal. For Ecol Manag 260:883–892CrossRefGoogle Scholar
  25. Fernandes P, Monteiro-Henriques T, Guiomar N, Loureiro C, Barros A (2016a) Bottom-up variables govern large-fire size in Portugal. Ecosystems 19:1362–1375CrossRefGoogle Scholar
  26. Fernandes P, Pacheco A, Almeida R, Claro J (2016b) The role of fire-suppression force in limiting the spread of extremely large forest fires in Portugal. Eur J For Res 135:253–262CrossRefGoogle Scholar
  27. Franklin J (2010) Mapping species distributions: spatial inference and prediction. Cambridge University Press, CambridgeCrossRefGoogle Scholar
  28. Fréjaville T, Curt T (2015) Spatiotemporal patterns of changes in fire regime and climate: defining the pyroclimates of south-eastern France (Mediterranean Basin). Clim Change 129:239–251CrossRefGoogle Scholar
  29. Ganteaume A, Jappiot M (2013) What causes large fires in Southern France. For Ecol Manag 294:76–85CrossRefGoogle Scholar
  30. Gill A, Allan G (2008) Large fires, fire effects and the fire-regime concept. Int J Wildland Fire 17:688–695CrossRefGoogle Scholar
  31. Gill A, Moore P (1998) Big versus small fires: the bushfires of greater Sydney January 1994. In: Moreno J (ed) Large forest fires. Backhuys Publishers, Leiden, pp 49–68Google Scholar
  32. Guo F, Zhang L, Jin S, Tigabu M, Su Z, Wang W (2016a) Modeling anthropogenic fire occurrence in the boreal forest of China using logistic regression and random forests. Forests 7:250CrossRefGoogle Scholar
  33. Guo F, Wang G, Su Z, Liang H, Wang W, Lin F, Liu A (2016b) What drives forest fire in Fujian, China? Evidence from logistic regression and Random Forests. J Wildland Fire 25:505–519CrossRefGoogle Scholar
  34. Hand D, Till R (2001) A simple generalization of the area under the ROC curve for multiple class classification problems. Mach Learn 45:171–186CrossRefGoogle Scholar
  35. Hanley J, McNeil B (1982) The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 143:29–36CrossRefGoogle Scholar
  36. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer, New YorkCrossRefGoogle Scholar
  37. Hawbaker T, Radeloff V, Stewart S, Hammer R, Keuler N, Clayton M (2013) Human and biophysical influences on fire occurrence in the United States. Ecol Appl 23:565–582CrossRefGoogle Scholar
  38. Hernandez C, Drobinski P, Turquety S, Dupuy J (2015) Size of wildfires in the Euro-Mediterranean region: observations and theoretical analysis. Nat Hazards Earth Syst Sci Discuss 15:1331–1341CrossRefGoogle Scholar
  39. Hijmans R, Cameron S, Parra J, Jones P, Jarvis A (2005) Very high resolution interpolated climate surfaces for global land areas. Int J Climatol 25:1965–1978CrossRefGoogle Scholar
  40. Hosmer D, Lemeshow S, Sturdivant R (2013) Applied logistic regression. Wiley, ChicesterCrossRefGoogle Scholar
  41. Jiang Y, Zhuang Q, Mandallaz D (2012) Large fire frequency and burned area in Canadian terrestrial ecosystems with poisson models. Environ Model Assess 17:483–493CrossRefGoogle Scholar
  42. Liu Z, Wimberly M (2015) Climatic and landscape influences on fire regimes from 1984 to 2010 in the western United States. PLoS ONE 10:e0140839CrossRefGoogle Scholar
  43. Liu M, Hu Y, Chang Y, He X, Zhang W (2009) Land use and land cover change analysis and prediction in the upper reaches of the Minjiang river, China. Environ Manag 43:899–907CrossRefGoogle Scholar
  44. Liu Z, Yang J, He H (2013) Identifying the threshold of dominant controls on fire spread in a boreal forest landscape of northeast China. PLoS ONE 8:e55618CrossRefGoogle Scholar
  45. Loepfe L, Martinez-Vilalta J, Oliveres J, Pinol J, Lloret F (2010) Feedbacks between fuel reduction and landscape homogenisation determine fire regimes in three Mediterranean areas. For Ecol Manag 259:2366–2374CrossRefGoogle Scholar
  46. Lutz J, Key C, Kolden C, Kane J, van Wagtendonk J (2011) Fire frequency, area burned, and severity: what is a normal fire year? Fire Ecol 7:51–65CrossRefGoogle Scholar
  47. Marchi E, Neri F, Tesi E, Fabiano F, Montorselli N (2014) Analysis of helicopter activities in forest fire-fighting. Croat J For Eng 35:233–243Google Scholar
  48. Martell D, Sun H (2008) The impact of fire suppression, vegetation and weather on the area burned by lightning-caused forest fires in Ontario. Can J For Res 38:1547–1563CrossRefGoogle Scholar
  49. McCune B, Grace J (2002) Analysis of ecological communities. MjM Software Design, Gleneden BeachGoogle Scholar
  50. Mitsopoulos I (2009) Forest fires analysis in Greece by using advanced multivariate statistical methods. Final Report. Post Ph.D. Research Grant. The State Scholarships Foundation-IKY. Athens. (in Greek with English abstract) Google Scholar
  51. Modugnoa S, Heiko Balzterb H, Coleb B, Borrellid P (2016) Mapping regional patterns of large forest fires in Wildland–Urban Interface areas in Europe. J Environ Manag 172:112–126CrossRefGoogle Scholar
  52. Moreira F, Catry F, Rego F, Bacao F (2010) Size-dependent pattern of wildfire ignitions in Portugal: when do ignitions turn into big fires? Landsc Ecol 25:1405–1417CrossRefGoogle Scholar
  53. Moreira F, Viedma O, Arianoutsou M, Curt T, Koutsias N, Rigolot F, Barbati A, Corona P, Vaz P, Xanthopoulos G, Mouillot F, Bilgili E (2011) Landscape–wildfire interactions in southern Europe: implications for landscape management. J Environ Manag 92:2389–2402CrossRefGoogle Scholar
  54. Moreno J, Vázquez A, Vélez R (1998) Recent history of forest fires in Spain. In: Moreno J (ed) Large forest fires. Backhuys Publishers, Leiden, pp 159–185Google Scholar
  55. Moreno M, Conedera M, Chuvieco E, Pezzatti G (2014) Fire regime changes and major driving forces in Spain from 1968 to 2010. Environ Sci Policy 37:11–22CrossRefGoogle Scholar
  56. Nunes M, Vasconcelos M, Pereira J, Dasgupta N, Alldredge R, Rego F (2005) Land cover types and fire in Portugal: do fires burn land cover selectively? Landsc Ecol 20:661–673CrossRefGoogle Scholar
  57. Oliveira S, Pereira J, Carreiras J (2012) Fire frequency analysis in Portugal (1975–2005), using Landsat-based burnt area maps. Int J Wildland Fire 21:48–60CrossRefGoogle Scholar
  58. Olsen C, Shindler B (2010) Trust, acceptance, and citizen–agency-interactions after large fires: influences on planning processes. Int J Wildland Fire 19:137–147CrossRefGoogle Scholar
  59. Parisien M, Parks S, Miller C, Krawchuk M, Heathcott M, Moritz M (2011) Contributions of ignitions, fuels, and weather to the spatial patterns of burn probability of a boreal landscape. Ecosystems 14:1141–1155CrossRefGoogle Scholar
  60. Pereira M, Trigo R, da Camara C, Pereira J, Leite S (2005) Synoptic patterns associated with large summer forest fires in Portugal. Agric For Meteorol 129:11–25CrossRefGoogle Scholar
  61. Podur J, Martell D (2007) A simulation model of the growth and suppression of large forest fires in Ontario. Int J Wildland Fire 16:285–294CrossRefGoogle Scholar
  62. Preisler H, Brillinger D, Burgan R, Benoit J (2004) Probability based models for estimating wildfire risk. Int J Wildland Fire 13:133–142CrossRefGoogle Scholar
  63. R Development Core Team (2008) R: A language and environment for statistical computing. R Foundation for Statistical Computing, ViennaGoogle Scholar
  64. Riley K, Abatzoglou J, Grenfell I, Klene A, Heinsch F (2013) The relationship of large fire occurrence with drought and fire danger indices in the western USA, 1984–2008: the role of temporal scale. Int J Wildland Fire 22:894–909CrossRefGoogle Scholar
  65. Rodrigues M, de la Riva J (2014) An insight into machine-learning algorithms to model human-caused wildfire occurrence. Environ Model Softw 57:192–201CrossRefGoogle Scholar
  66. Rothermel R (1983) How to predict the spread and intensity of forest and range fires. In: General Technical Report INT-143 USDA, Forest Service, Intermountain Forest and Range Experiment Station, OgdenGoogle Scholar
  67. Ruffault J, Moron V, Trigo R, Curt T (2016) Daily synoptic conditions associated with large fire occurrence in Mediterranean France: evidence for a wind-driven fire regime. Int J Climatol 37(1):524–533CrossRefGoogle Scholar
  68. San-Miguel-Ayanz J, Moreno J, Camia A (2013) Analysis of large fires in European Mediterranean landscapes: lessons learned and perspectives. For Ecol Manag 294:11–22CrossRefGoogle Scholar
  69. Sørensen R, Zinko U, Seibert J (2006) On the calculation of the topographic wetness index: evaluation of different methods based on field observations. Hydrol Earth Syst Sci 10:101–112CrossRefGoogle Scholar
  70. Stocks B, Mason J, Todd J, Bosch E, Wotton B, Amiro B, Flannigan M, Hirsch K, Logan K, Martell D, Skinner W (2002) Large forest fires in Canada, 1959–1997. J Geophys Res 108:8149CrossRefGoogle Scholar
  71. Van Wagner C (1987) Development and structure of the Canadian forest fire weather index system. Forest Technology Report 35, OttawaGoogle Scholar
  72. Vázquez A, Moreno J (2001) Spatial distribution of forest fires in Sierra de Gredos (Central Spain). For Ecol Manag 147:55–65CrossRefGoogle Scholar
  73. Viedma O, Quesada J, Torres I, DeSantis A, Moreno J (2015) Fire severity in a large fire in a Pinus pinaster forest is highly predictable from burning conditions, stand structure, and topography. Ecosystems 18:237–250CrossRefGoogle Scholar
  74. Viegas D (1998) Weather, fuel status and fire occurrence: predicting large fires. In: Moreno J (ed) Large forest fires. Backhuys Publishers, Leiden, pp 31–48Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2017

Authors and Affiliations

  1. 1.The Global Fire Monitoring Center (GFMC), Fire Ecology Research Groupc/o Freiburg UniversityFreiburgGermany
  2. 2.Department of Biodiversity and Protected AreasMinistry of Environment and EnergyAthensGreece
  3. 3.Laboratory of Forest Remote Sensing, Department of Forestry and Management of the Environment and Natural ResourcesDemocritus University of ThraceOrestiadaGreece

Personalised recommendations